{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZNTYPDPY3XDER6MVXJ6KPDXRQK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89ae730f2fedf5aa2f01ca5a9c2b586d41edb60566e525747dc40cedba8e1e87","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-15T14:07:41Z","title_canon_sha256":"7d478e55b31630e52b20582bd0b45848083353ef7bcae8c651318bab349ba6b3"},"schema_version":"1.0","source":{"id":"2308.07787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07787","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07787v1","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07787","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZNTYPDPY3XDE","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZNTYPDPY3XDER6MV","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZNTYPDPY","created_at":"2026-07-05T06:41:31Z"}],"graph_snapshots":[{"event_id":"sha256:cc4f9a133d2e6150e27140f3b6f1721b533fdd358a0d88a708f03846b3ed2251","target":"graph","created_at":"2026-07-05T06:41:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.07787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has demonstrated impressive results in video-to-speech synthesis which involves reconstructing speech solely from visual input. However, previous works have struggled to accurately synthesize speech due to a lack of sufficient guidance for the model to infer the correct content with the appropriate sound. To resolve the issue, they have adopted an extra speaker embedding as a speaking style guidance from a reference auditory information. Nevertheless, it is not always possible to obtain the audio information from the corresponding video input, especially during the inference ti","authors_text":"Jeongsoo Choi, Joanna Hong, Yong Man Ro","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-15T14:07:41Z","title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07787","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a98a9842a95cc580d5c4a9c8a323fd6167a418eb5e606f00530eb8825d10f515","target":"record","created_at":"2026-07-05T06:41:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"89ae730f2fedf5aa2f01ca5a9c2b586d41edb60566e525747dc40cedba8e1e87","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-15T14:07:41Z","title_canon_sha256":"7d478e55b31630e52b20582bd0b45848083353ef7bcae8c651318bab349ba6b3"},"schema_version":"1.0","source":{"id":"2308.07787","kind":"arxiv","version":1}},"canonical_sha256":"cb67878df8ddc648f995ba7ca78ef182b2a1a2454a881d68014fdecb9eb9f6bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb67878df8ddc648f995ba7ca78ef182b2a1a2454a881d68014fdecb9eb9f6bc","first_computed_at":"2026-07-05T06:41:31.350839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:31.350839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KxCaoKqh1ghH3Gw8jX8qqqmKppQRNrmFQfNcKEN3gDnW/tHhcfYI6vhaRQxqOdJ2tlT5NQ9d9OquAc2GGgNlAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:31.351311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.07787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a98a9842a95cc580d5c4a9c8a323fd6167a418eb5e606f00530eb8825d10f515","sha256:cc4f9a133d2e6150e27140f3b6f1721b533fdd358a0d88a708f03846b3ed2251"],"state_sha256":"c004359a9f5d8fa15dc5cf719dda99cd144c9464441c7b9bd96ca08cb4b95614"}